t5-small-finetuned-logjuicer

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.8674
• Rouge1: 18.6355
• Rouge2: 12.317
• Rougel: 18.4432
• Rougelsum: 18.4298
• Gen Len: 19.0

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	46	3.9203	7.8841	1.7456	7.5043	7.9956	19.0
No log	2.0	92	3.3239	7.8589	1.7456	7.4779	7.9585	19.0
No log	3.0	138	2.9555	7.7528	3.0412	7.7043	7.7184	19.0
No log	4.0	184	2.7069	8.6355	3.8093	8.5839	8.6118	19.0
No log	5.0	230	2.5137	8.6983	3.9184	8.5872	8.6149	19.0
No log	6.0	276	2.3425	11.6364	4.355	11.1532	11.2938	19.0
No log	7.0	322	2.2153	19.4997	5.9307	17.2555	18.1446	19.0
No log	8.0	368	2.1213	19.3399	6.09	17.1197	18.0052	19.0
No log	9.0	414	2.0448	18.6986	8.2548	17.2942	17.7272	19.0
No log	10.0	460	1.9893	18.3085	11.359	17.9649	17.9785	19.0
2.9395	11.0	506	1.9429	18.1059	11.6297	17.8684	17.9266	19.0
2.9395	12.0	552	1.9091	18.3172	12.0275	18.1818	18.1678	19.0
2.9395	13.0	598	1.8859	18.5764	12.2624	18.3462	18.3067	19.0
2.9395	14.0	644	1.8717	18.626	12.3128	18.4411	18.4202	19.0
2.9395	15.0	690	1.8674	18.6355	12.317	18.4432	18.4298	19.0

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2